hooks_pretrain · Claude Flow MCP: Risk & Policy

WHAT IT DOES

What hooks_pretrain does on Claude Flow

AI agents invoke hooks_pretrain to trigger actions in Claude Flow. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why hooks_pretrain needs a policy

The tool runs a multi-step pipeline that analyzes a repository and bootstraps intelligence using native Bash hooks. This involves executing code/scripts against a codebase, which qualifies as Execute. The Bash hook execution aspect introduces significant risk — an AI agent could trigger arbitrary shell operations across a repository.

From the tool's definition 'Analyze repository to bootstrap intelligence (4-step pipeline)' and 'native Bash hooks (via Claude Code'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

hooks_pretrain Rate-limited

hooks_pretrain stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "hooks_pretrain": {
      "limits": [
        {
          "counter": "hooks_pretrain_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Flow, so you can run agents against it safely.

FAQ

Questions about hooks_pretrain

What does the hooks_pretrain tool do? +

Analyze repository to bootstrap intelligence (4-step pipeline) Use when native Bash hooks (via Claude Code\. It is categorised as a Execute tool in the Claude Flow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on hooks_pretrain? +

Register the Claude Flow MCP server in PolicyLayer and add a rule for hooks_pretrain: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Claude Flow. Nothing to install.

What risk level is hooks_pretrain? +

hooks_pretrain is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit hooks_pretrain? +

Yes. Add a rate_limit block to the hooks_pretrain rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block hooks_pretrain completely? +

Set action: deny in the PolicyLayer policy for hooks_pretrain. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides hooks_pretrain? +

hooks_pretrain is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.